Cargando…
Optimizing 3D Convolution Kernels on Stereo Matching for Resource Efficient Computations
Despite recent stereo matching algorithms achieving significant results on public benchmarks, the problem of requiring heavy computation remains unsolved. Most works focus on designing an architecture to reduce the computational complexity, while we take aim at optimizing 3D convolution kernels on t...
Autores principales: | Xiao, Jianqiang, Ma, Dianbo, Yamane, Satoshi |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8537023/ https://www.ncbi.nlm.nih.gov/pubmed/34696021 http://dx.doi.org/10.3390/s21206808 |
Ejemplares similares
-
Depth Estimation for Light-Field Images Using Stereo Matching and Convolutional Neural Networks
por: Rogge, Ségolène, et al.
Publicado: (2020) -
A Comparison and Evaluation of Stereo Matching on Active Stereo Images
por: Jang, Mingyu, et al.
Publicado: (2022) -
A Joint 2D-3D Complementary Network for Stereo Matching
por: Jia, Xiaogang, et al.
Publicado: (2021) -
Widening siamese architectures for stereo matching
por: Brandao, Patrick, et al.
Publicado: (2019) -
Resource-oriented computing with NetKernel
por: Geudens, Tom
Publicado: (2012)